← Learning Types
Machine Learning › Learning Types ›

Adversarial Learning

4854 directly classified papers

Papers per year

Papers

Rethinking Backdoor Detection Evaluation for Language Models EMNLP 2025
Adversarial Robust Memory-Based Continual Learner ICCV 2025
SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025
AIP: Subverting Retrieval-Augmented Generation via Adversarial Instructional Prompt EMNLP 2025
Phi: Preference Hijacking in Multi-modal Large Language Models at Inference Time EMNLP 2025
TempParaphraser: “Heating Up” Text to Evade AI-Text Detection through Paraphrasing EMNLP 2025
IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization ICCV 2025
NEXUS: Network Exploration for eXploiting Unsafe Sequences in Multi-Turn LLM Jailbreaks EMNLP 2025
Transitive self-consistency evaluation of NLI models without gold labels EMNLP 2025
AAKR: Adversarial Attack-based Knowledge Retention for Continual Semantic Segmentation AAAI 2025
Enhancing Chinese Offensive Language Detection with Homophonic Perturbation EMNLP 2025
PLA: Prompt Learning Attack against Text-to-Image Generative Models ICCV 2025
CAMH: Advancing Model Hijacking Attack in Machine Learning AAAI 2025
Same Question, Different Words: A Latent Adversarial Framework for Prompt Robustness EMNLP 2025
Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding EMNLP 2025
Generative Adversarial Diffusion ICCV 2025
ODDR: Outlier Detection & Dimension Reduction Based Defense Against Adversarial Patches ICCV 2025
Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking EMNLP 2025
RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors ICCV 2025
Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning EMNLP 2025
TimeBooth: Disentangled Facial Invariant Representation for Diverse and Personalized Face Aging ICCV 2025
Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor AAAI 2025
Agent vs. Agent: Automated Data Generation and Red-Teaming for Custom Agentic Workflows EMNLP 2025
SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures ICCV 2025
Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting AAAI 2025